2
$\begingroup$

Tell me if there are any w2v models that do not require a dictionary. So, everything that I found in torchtext first wants to know the dictionary build_vocab. But if I have a huge body of text, I would like to have a model that works at the level of phrases. But I did not find one.

$\endgroup$
2
  • $\begingroup$ No. For a given word or a phrase word2vec needs a way to look up its vector. $\endgroup$
    – Valentas
    Feb 15, 2019 at 18:53
  • $\begingroup$ If I create letter2vec and after that I create new vectors from letter2vec $\endgroup$ Feb 15, 2019 at 19:51

1 Answer 1

0
$\begingroup$

Every word2vec model requires a dictionary that maps an index to a string literal. This dictionary mapping greatly speeds up training because the training is completely integer-based.

The string literal values can be any length, from individual characters to phrases.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.